Time-Wise Attention Aided Convolutional Neural Network for Data-Driven Cellular Traffic Prediction

dc.contributor.authorShen, Wenxin
dc.contributor.authorZhang, Haixia
dc.contributor.authorGuo, Shuaishuai
dc.contributor.authorZhang, Chuanting
dc.contributor.departmentComputer, Electrical and Mathematical Science and Engineering (CEMSE) Division
dc.contributor.departmentSchool of Control Science and Engineering, Shandong University, Jinan 250061, China, and also with Shandong Provincial Key Laboratory of Wireless Communication Technologies, Shandong University, Jinan 250100, China. C. Zhang is with Computer, Electrical and Mathematical Sciences and Engineering division, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia.
dc.date.accessioned2021-05-24T10:32:33Z
dc.date.available2021-05-24T10:32:33Z
dc.date.issued2021-05-10
dc.date.published-online2021-05-10
dc.date.published-print2021-08
dc.description.abstractRecurrent neural network (RNN) based models are widely adopted to capture temporal dependencies in the state-of-the-art approaches for cellular traffic prediction. However, RNN is inefficient and incapable of capturing long-range temporal dependencies of traffic data. Besides, its inherent sequential nature makes it time consuming in capture the temporal dependencies. To better capture the long-term temporal dependency and reduce the consumed time in traffic data prediction, we propose a time-wise attention aided convolutional neural network (TWACNet) structure for cellular traffic prediction. In the proposed TWACNet, the time-wise attention mechanism is adopted to capture long-range temporal dependencies of the cellular traffic data and the convolutional neural network (CNN) is adopted to capture the spatial correlation. The performance of TWACNet in traffic prediction is tested in real-world cellular traffic datasets. Experimental results demonstrate that our proposed approach can considerably outperform those existing prediction methods in terms of root mean square errors (RMSE) and training time.
dc.description.sponsorshipThe work presented in this paper was supported in part by the Project of International Cooperation and Exchanges NSFC under Grant No. 61860206005.
dc.eprint.versionPost-print
dc.identifier.citationShen, W., Zhang, H., Guo, S., & Zhang, C. (2021). Time-Wise Attention Aided Convolutional Neural Network for Data-Driven Cellular Traffic Prediction. IEEE Wireless Communications Letters, 1–1. doi:10.1109/lwc.2021.3078745
dc.identifier.doi10.1109/LWC.2021.3078745
dc.identifier.eid2-s2.0-85105865279
dc.identifier.issn2162-2345
dc.identifier.issn2162-2337
dc.identifier.journalIEEE Wireless Communications Letters
dc.identifier.pages1-1
dc.identifier.urihttp://hdl.handle.net/10754/669230
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.relation.urlhttps://ieeexplore.ieee.org/document/9427172/
dc.rights(c) 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
dc.titleTime-Wise Attention Aided Convolutional Neural Network for Data-Driven Cellular Traffic Prediction
dc.typeArticle
display.details.left<span><h5>Type</h5>Article<br><br><h5>Authors</h5><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.author=Shen, Wenxin,equals">Shen, Wenxin</a><br><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.author=Zhang, Haixia,equals">Zhang, Haixia</a><br><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.author=Guo, Shuaishuai,equals">Guo, Shuaishuai</a><br><a href="https://repository.kaust.edu.sa/search?query=orcid.id:0000-0002-6685-4071&spc.sf=dc.date.issued&spc.sd=DESC">Zhang, Chuanting</a> <a href="https://orcid.org/0000-0002-6685-4071" target="_blank"><img src="https://repository.kaust.edu.sa/server/api/core/bitstreams/82a625b4-ed4b-40c8-865a-d6a5225a26a4/content" width="16" height="16"/></a><br><br><h5>KAUST Department</h5><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.department=Computer, Electrical and Mathematical Science and Engineering (CEMSE) Division,equals">Computer, Electrical and Mathematical Science and Engineering (CEMSE) Division</a><br><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.department=School of Control Science and Engineering, Shandong University, Jinan 250061, China, and also with Shandong Provincial Key Laboratory of Wireless Communication Technologies, Shandong University, Jinan 250100, China. C. Zhang is with Computer, Electrical and Mathematical Sciences and Engineering division, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia.,equals">School of Control Science and Engineering, Shandong University, Jinan 250061, China, and also with Shandong Provincial Key Laboratory of Wireless Communication Technologies, Shandong University, Jinan 250100, China. C. Zhang is with Computer, Electrical and Mathematical Sciences and Engineering division, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia.</a><br><br><h5>Online Publication Date</h5>2021-05-10<br><br><h5>Print Publication Date</h5>2021-08<br><br><h5>Date</h5>2021-05-10</span>
display.details.right<span><h5>Abstract</h5>Recurrent neural network (RNN) based models are widely adopted to capture temporal dependencies in the state-of-the-art approaches for cellular traffic prediction. However, RNN is inefficient and incapable of capturing long-range temporal dependencies of traffic data. Besides, its inherent sequential nature makes it time consuming in capture the temporal dependencies. To better capture the long-term temporal dependency and reduce the consumed time in traffic data prediction, we propose a time-wise attention aided convolutional neural network (TWACNet) structure for cellular traffic prediction. In the proposed TWACNet, the time-wise attention mechanism is adopted to capture long-range temporal dependencies of the cellular traffic data and the convolutional neural network (CNN) is adopted to capture the spatial correlation. The performance of TWACNet in traffic prediction is tested in real-world cellular traffic datasets. Experimental results demonstrate that our proposed approach can considerably outperform those existing prediction methods in terms of root mean square errors (RMSE) and training time.<br><br><h5>Citation</h5>Shen, W., Zhang, H., Guo, S., & Zhang, C. (2021). Time-Wise Attention Aided Convolutional Neural Network for Data-Driven Cellular Traffic Prediction. IEEE Wireless Communications Letters, 1–1. doi:10.1109/lwc.2021.3078745<br><br><h5>Acknowledgements</h5>The work presented in this paper was supported in part by the Project of International Cooperation and Exchanges NSFC under Grant No. 61860206005.<br><br><h5>Publisher</h5><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.publisher=Institute of Electrical and Electronics Engineers (IEEE),equals">Institute of Electrical and Electronics Engineers (IEEE)</a><br><br><h5>Journal</h5><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.journal=IEEE Wireless Communications Letters,equals">IEEE Wireless Communications Letters</a><br><br><h5>DOI</h5><a href="https://doi.org/10.1109/LWC.2021.3078745">10.1109/LWC.2021.3078745</a><br><br><h5>Additional Links</h5>https://ieeexplore.ieee.org/document/9427172/</span>
kaust.personShen, Wenxin
kaust.personZhang, Haixia
kaust.personGuo, Shuaishuai
kaust.personZhang, Chuanting
orcid.authorShen, Wenxin
orcid.authorZhang, Haixia
orcid.authorGuo, Shuaishuai
orcid.authorZhang, Chuanting::0000-0002-6685-4071
orcid.id0000-0002-6685-4071
Files